pi/openvins_linux
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

initial commit

Browse Source
This commit is contained in:
Иван Подмогильный
2022-08-05 08:23:25 +03:00
commit 5ecdc6abcf
387 changed files with 3010095 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

243
docs/gs-datasets.dox Normal file
View File

@@ -0,0 +1,243 @@
/**
@page gs-datasets Supported Datasets
@tableofcontents
@section gs-data-euroc The EuRoC MAV Dataset
The ETH ASL [EuRoC MAV dataset](https://projects.asl.ethz.ch/datasets/doku.php?id=kmavvisualinertialdatasets) @cite Burri2016IJRR is one of the most used datasets in the visual-inertial / simultaneous localization and mapping (SLAM) research literature.
The reason for this is the synchronised inertial+camera sensor data and the high quality groundtruth.
The dataset contains different sequences of varying difficulty of a Micro Aerial Vehicle (MAV) flying in an indoor room.
Monochrome stereo images are collected by a two Aptina MT9V034 global shutter cameras at 20 frames per seconds, while a ADIS16448 MEMS inertial unit provides linear accelerations and angular velocities at a rate of 200 samples per second.
We recommend that most users start testing on this dataset before moving on to the other datasets that our system support or before trying with your own collected data.
The machine hall datasets have the MAV being picked up in the beginning and then set down, we normally skip this part, but it should be able to be handled by the filter if SLAM features are enabled.
Please take a look at the [run_ros_eth.sh](https://github.com/rpng/open_vins/blob/master/ov_msckf/scripts/run_ros_eth.sh) script for some reasonable default values (they might still need to be tuned).
@m_class{m-block m-warning}
@par Groundtruth on V1_01_easy
We have found that the groundtruth on the V1_01_easy dataset is not accurate in its orientation estimate.
We have recomputed this by optimizing the inertial and vicon readings in a graph to get the trajectory of the imu.
You can find the output at this [link](https://drive.google.com/drive/folders/1d62Q_RQwHzKLcIdUlTeBmojr7j0UL4sM?usp=sharing) and is what we normally use to evaluate the error on this dataset.
@m_div{m-text-center}
| Dataset Name | Length (m) | Dataset Link | Groundtruth Traj. | Config |
|-------------:|--------|--------------|------------------|------------------|
| Vicon Room 1 01 | 58 | [rosbag](http://robotics.ethz.ch/~asl-datasets/ijrr_euroc_mav_dataset/vicon_room1/V1_01_easy/V1_01_easy.bag), [rosbag2](https://drive.google.com/drive/folders/1xQ1KcZhZ5pioPXTyrZBN6Mjxkfpcd_B3?usp=sharing) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/euroc_mav) | [config](https://github.com/rpng/open_vins/blob/master/config/euroc_mav) |
| Vicon Room 1 02 | 76 | [rosbag](http://robotics.ethz.ch/~asl-datasets/ijrr_euroc_mav_dataset/vicon_room1/V1_02_medium/V1_02_medium.bag) , [rosbag2](https://drive.google.com/drive/folders/1xQ1KcZhZ5pioPXTyrZBN6Mjxkfpcd_B3?usp=sharing)| [link](https://github.com/rpng/open_vins/tree/master/ov_data/euroc_mav) | [config](https://github.com/rpng/open_vins/blob/master/config/euroc_mav) |
| Vicon Room 1 03 | 79 | [rosbag](http://robotics.ethz.ch/~asl-datasets/ijrr_euroc_mav_dataset/vicon_room1/V1_03_difficult/V1_03_difficult.bag), [rosbag2](https://drive.google.com/drive/folders/1xQ1KcZhZ5pioPXTyrZBN6Mjxkfpcd_B3?usp=sharing) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/euroc_mav) | [config](https://github.com/rpng/open_vins/blob/master/config/euroc_mav) |
| Vicon Room 2 01 | 37 | [rosbag](http://robotics.ethz.ch/~asl-datasets/ijrr_euroc_mav_dataset/vicon_room2/V2_01_easy/V2_01_easy.bag), [rosbag2](https://drive.google.com/drive/folders/1xQ1KcZhZ5pioPXTyrZBN6Mjxkfpcd_B3?usp=sharing) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/euroc_mav) | [config](https://github.com/rpng/open_vins/blob/master/config/euroc_mav) |
| Vicon Room 2 02 | 83 | [rosbag](http://robotics.ethz.ch/~asl-datasets/ijrr_euroc_mav_dataset/vicon_room2/V2_02_medium/V2_02_medium.bag), [rosbag2](https://drive.google.com/drive/folders/1xQ1KcZhZ5pioPXTyrZBN6Mjxkfpcd_B3?usp=sharing) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/euroc_mav) | [config](https://github.com/rpng/open_vins/blob/master/config/euroc_mav) |
| Vicon Room 2 03 | 86 | [rosbag](http://robotics.ethz.ch/~asl-datasets/ijrr_euroc_mav_dataset/vicon_room2/V2_03_difficult/V2_03_difficult.bag), [rosbag2](https://drive.google.com/drive/folders/1xQ1KcZhZ5pioPXTyrZBN6Mjxkfpcd_B3?usp=sharing) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/euroc_mav) | [config](https://github.com/rpng/open_vins/blob/master/config/euroc_mav) |
| Machine Hall 01 | 80 | [rosbag](http://robotics.ethz.ch/~asl-datasets/ijrr_euroc_mav_dataset/machine_hall/MH_01_easy/MH_01_easy.bag), [rosbag2](https://drive.google.com/drive/folders/1xQ1KcZhZ5pioPXTyrZBN6Mjxkfpcd_B3?usp=sharing) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/euroc_mav) | [config](https://github.com/rpng/open_vins/blob/master/config/euroc_mav) |
| Machine Hall 02 | 73 | [rosbag](http://robotics.ethz.ch/~asl-datasets/ijrr_euroc_mav_dataset/machine_hall/MH_02_easy/MH_02_easy.bag), [rosbag2](https://drive.google.com/drive/folders/1xQ1KcZhZ5pioPXTyrZBN6Mjxkfpcd_B3?usp=sharing) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/euroc_mav) | [config](https://github.com/rpng/open_vins/blob/master/config/euroc_mav) |
| Machine Hall 03 | 131 | [rosbag](http://robotics.ethz.ch/~asl-datasets/ijrr_euroc_mav_dataset/machine_hall/MH_03_medium/MH_03_medium.bag), [rosbag2](https://drive.google.com/drive/folders/1xQ1KcZhZ5pioPXTyrZBN6Mjxkfpcd_B3?usp=sharing) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/euroc_mav) | [config](https://github.com/rpng/open_vins/blob/master/config/euroc_mav) |
| Machine Hall 04 | 92 | [rosbag](http://robotics.ethz.ch/~asl-datasets/ijrr_euroc_mav_dataset/machine_hall/MH_04_difficult/MH_04_difficult.bag), [rosbag2](https://drive.google.com/drive/folders/1xQ1KcZhZ5pioPXTyrZBN6Mjxkfpcd_B3?usp=sharing) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/euroc_mav) | [config](https://github.com/rpng/open_vins/blob/master/config/euroc_mav) |
| Machine Hall 05 | 98 | [rosbag](http://robotics.ethz.ch/~asl-datasets/ijrr_euroc_mav_dataset/machine_hall/MH_05_difficult/MH_05_difficult.bag), [rosbag2](https://drive.google.com/drive/folders/1xQ1KcZhZ5pioPXTyrZBN6Mjxkfpcd_B3?usp=sharing) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/euroc_mav) | [config](https://github.com/rpng/open_vins/blob/master/config/euroc_mav) |
@m_enddiv
@section gs-data-tumvi TUM Visual-Inertial Dataset
The TUM [Visual-Inertial Dataset](https://vision.in.tum.de/data/datasets/visual-inertial-dataset) @cite Schubert2018IROS is a more recent dataset that was presented to provide a way to evaluate state-of-the-art visual inertial odometry approaches.
As compared to the EuRoC MAV datasets, this dataset provides photometric calibration of the cameras which has not been available in any other visual-inertal dataset for researchers.
Monochrome stereo images are collected by two IDS uEye UI-3241LE-M-GL global shutter cameras at 20 frames per second, while a Bosch BMI160 inertial unit provides linear accelerations and angular velocities at a rate of 200 samples per second.
Not all datasets have groundtruth available throughout the entire trajectory as the motion capture system is limited to the starting and ending room.
There are quite a few very challenging outdoor handheld datasets which are a challenging direction for research.
Note that we focus on the room datasets as full 6 dof pose collection is available over the total trajectory.
@m_class{m-block m-warning}
@par Filter Initialization from Standstill
These datasets have very non-static starts, as they are handheld, and the standstill initialization has issues handling this.
Thus careful tuning of the imu initialization threshold is typically needed to ensure that the initialized orientation and the zero velocity assumption are valid.
Please take a look at the [run_ros_tumvi.sh](https://github.com/rpng/open_vins/blob/master/ov_msckf/scripts/run_ros_tumvi.sh) script for some reasonable default values (they might still need to be tuned).
@m_div{m-text-center}
| Dataset Name | Length (m) | Dataset Link | Groundtruth Traj. | Config |
|-------------:|--------|--------------|------------------|------------------|
| room1 | 147 | [rosbag](http://vision.in.tum.de/tumvi/calibrated/512_16/dataset-room1_512_16.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/tum_vi) | [config](https://github.com/rpng/open_vins/blob/master/config/tum_vi) |
| room2 | 142 | [rosbag](http://vision.in.tum.de/tumvi/calibrated/512_16/dataset-room2_512_16.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/tum_vi) | [config](https://github.com/rpng/open_vins/blob/master/config/tum_vi) |
| room3 | 136 | [rosbag](http://vision.in.tum.de/tumvi/calibrated/512_16/dataset-room3_512_16.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/tum_vi) | [config](https://github.com/rpng/open_vins/blob/master/config/tum_vi) |
| room4 | 69 | [rosbag](http://vision.in.tum.de/tumvi/calibrated/512_16/dataset-room4_512_16.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/tum_vi) | [config](https://github.com/rpng/open_vins/blob/master/config/tum_vi) |
| room5 | 132 | [rosbag](http://vision.in.tum.de/tumvi/calibrated/512_16/dataset-room5_512_16.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/tum_vi) | [config](https://github.com/rpng/open_vins/blob/master/config/tum_vi) |
| room6 | 67 | [rosbag](http://vision.in.tum.de/tumvi/calibrated/512_16/dataset-room6_512_16.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/tum_vi) | [config](https://github.com/rpng/open_vins/blob/master/config/tum_vi) |
@m_enddiv
@section gs-data-rpng RPNG OpenVINS Dataset
In additional the community maintained datasets, we have also released a few datasets.
Please cite the OpenVINS paper if you use any of these datasets in your works.
Here are the specifics of the sensors that each dataset uses:
- ArUco Datasets:
- Core visual-inertial sensor is the [VI-Sensor](https://furgalep.github.io/bib/nikolic_icra14.pdf)
- Stereo global shutter images at 20 Hz
- ADIS16448 IMU at 200 Hz
- Kalibr calibration file can be found [here](https://drive.google.com/file/d/1I0C-z3ZrTKne4bdbgBI6CtH1Rk4EQim0/view?usp=sharing)
- Ironsides Datasets:
- Core visual-inertial sensor is the [ironsides](https://arxiv.org/pdf/1710.00893v1.pdf)
- Has two [Reach RTK](https://docs.emlid.com/reach/) one subscribed to a base station for corrections
- Stereo global shutter fisheye images at 20 Hz
- InvenSense IMU at 200 Hz
- GPS fixes at 5 Hz (/reach01/tcpfix has corrections from [NYSNet](https://cors.dot.ny.gov/sbc))
- Kalibr calibration file can be found [here](https://drive.google.com/file/d/1bhn0GrIYNEeAabQAbWoP8l_514cJ0KrZ/view?usp=sharing)
@m_class{m-block m-warning}
@par Monocular Camera
Currently there are issues with running with a monocular camera on the Ironside Neighborhood car datasets.
This is likely due to the near-constant velocity and "smoothness" of the trajectory.
Please refer to @cite Lee2020IROS and @cite Wu2017ICRA for details.
Most of these datasets do not have perfect calibration parameters, and some are not time synchronised.
Thus, please ensure that you have enabled online calibration of these parameters.
Additionally, there is no groundtruth for these datasets, but some do include GPS messages if you wish to compare relative to something.
@m_div{m-text-center}
| Dataset Name | Length (m) | Dataset Link | Groundtruth Traj. | Config |
|-------------:|--------|--------------|------------------|------------------|
| ArUco Room 01 | 27 | [rosbag](https://drive.google.com/file/d/1ytjo8V6pCroaVd8-QSop7R4DbsvvKyRQ/view?usp=sharing) | none | [config aruco](https://github.com/rpng/open_vins/blob/master/config/rpng_aruco) |
| ArUco Room 02 | 93 | [rosbag](https://drive.google.com/file/d/1l_hnPUW6ufqxPtrLqRRHHI4mfGRZB1ha/view?usp=sharing) | none | [config aruco](https://github.com/rpng/open_vins/blob/master/config/rpng_aruco) |
| ArUco Hallway 01 | 190 | [rosbag](https://drive.google.com/file/d/1FQBo3uHqRd0qm8GUb50Q-sj5gukcwaoU/view?usp=sharing) | none | [config aruco](https://github.com/rpng/open_vins/blob/master/config/rpng_aruco) |
| ArUco Hallway 02 | 105 | [rosbag](https://drive.google.com/file/d/1oAbnV3MPOeaUSjnSc3g8t-pWV1nVjbys/view?usp=sharing) | none | [config aruco](https://github.com/rpng/open_vins/blob/master/config/rpng_aruco) |
| Neighborhood 01 | 2300 | [rosbag](https://drive.google.com/file/d/1N07SDbaLEkq9pVEvi6oiHpavaRuFs3j2/view?usp=sharing) | none | [config ironsides](https://github.com/rpng/open_vins/blob/master/config/rpng_ironsides) |
| Neighborhood 02 | 7400 | [rosbag](https://drive.google.com/file/d/1QEUi40sO8OkVXEGF5JojiiZMHMSiSqtg/view?usp=sharing) | none | [config ironsides](https://github.com/rpng/open_vins/blob/master/config/rpng_ironsides) |
@m_enddiv
@section gs-data-uzhfpv UZH-FPV Drone Racing Dataset
The [UZH-FPV Drone Racing Dataset](https://fpv.ifi.uzh.ch/) @cite Schubert2018IROS is a dataset focused on high-speed agressive 6dof motion with very high levels of optical flow as compared to other datasets.
A FPV drone racing quadrotor has on board a Qualcomm Snapdragon Flight board which can provide inertial measurement and has two 640x480 grayscale global shutter fisheye camera's attached.
The groundtruth is collected with a Leica Nova MS60 laser tracker.
There are four total sensor configurations and calibration provides including: indoor forward facing stereo, indoor 45 degree stereo, outdoor forward facing, and outdoor 45 degree.
A top speed of 12.8 m/s (28 mph) is reached in the indoor scenarios, and 23.4 m/s (54 mphs) is reached in the outdoor datasets.
Each of these datasets is picked up in the beginning and then set down, we normally skip this part, but it should be able to be handled by the filter if SLAM features are enabled.
Please take a look at the [run_ros_uzhfpv.sh](https://github.com/rpng/open_vins/blob/master/ov_msckf/scripts/run_ros_uzhfpv.sh) script for some reasonable default values (they might still need to be tuned).
@m_class{m-block m-warning}
@par Dataset Groundtruthing
Only the Absolute Trajectory Error (ATE) should be used as a metric for this dataset.
This is due to inaccurate groundtruth orientation estimates which are explain in their [report](https://fpv.ifi.uzh.ch/wp-content/uploads/2020/11/Ground-Truth-Rotation-Issue-Report.pdf) on the issue.
The basic summary is that it is hard to get an accurate orientation information due to the point-based Leica measurements used to groundtruth.
@m_div{m-text-center}
| Dataset Name | Length (m) | Dataset Link | Groundtruth Traj. | Config |
|-------------:|--------|--------------|------------------|------------------|
| Indoor 5 | 157 | [rosbag](http://rpg.ifi.uzh.ch/datasets/uzh-fpv-newer-versions/v2/indoor_forward_5_snapdragon_with_gt.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/uzh_fpv) | [config](https://github.com/rpng/open_vins/blob/master/config/uzhfpv_indoor) |
| Indoor 6 | 204 | [rosbag](http://rpg.ifi.uzh.ch/datasets/uzh-fpv-newer-versions/v2/indoor_forward_6_snapdragon_with_gt.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/uzh_fpv) | [config](https://github.com/rpng/open_vins/blob/master/config/uzhfpv_indoor) |
| Indoor 7 | 314 | [rosbag](http://rpg.ifi.uzh.ch/datasets/uzh-fpv-newer-versions/v2/indoor_forward_7_snapdragon_with_gt.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/uzh_fpv) | [config](https://github.com/rpng/open_vins/blob/master/config/uzhfpv_indoor) |
| Indoor 9 | 136 | [rosbag](http://rpg.ifi.uzh.ch/datasets/uzh-fpv-newer-versions/v2/indoor_forward_9_snapdragon_with_gt.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/uzh_fpv) | [config](https://github.com/rpng/open_vins/blob/master/config/uzhfpv_indoor) |
| Indoor 10 | 129 | [rosbag](http://rpg.ifi.uzh.ch/datasets/uzh-fpv-newer-versions/v2/indoor_forward_10_snapdragon_with_gt.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/uzh_fpv) | [config](https://github.com/rpng/open_vins/blob/master/config/uzhfpv_indoor) |
| Indoor 45deg 2 | 207 | [rosbag](http://rpg.ifi.uzh.ch/datasets/uzh-fpv-newer-versions/v2/indoor_45_2_snapdragon_with_gt.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/uzh_fpv) | [config](https://github.com/rpng/open_vins/blob/master/config/uzhfpv_indoor_45) |
| Indoor 45deg 4 | 164 | [rosbag](http://rpg.ifi.uzh.ch/datasets/uzh-fpv-newer-versions/v2/indoor_45_4_snapdragon_with_gt.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/uzh_fpv) | [config](https://github.com/rpng/open_vins/blob/master/config/uzhfpv_indoor_45) |
| Indoor 45deg 12 | 112 | [rosbag](http://rpg.ifi.uzh.ch/datasets/uzh-fpv-newer-versions/v2/indoor_45_12_snapdragon_with_gt.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/uzh_fpv) | [config](https://github.com/rpng/open_vins/blob/master/config/uzhfpv_indoor_45) |
| Indoor 45deg 13 | 159 | [rosbag](http://rpg.ifi.uzh.ch/datasets/uzh-fpv-newer-versions/v2/indoor_45_13_snapdragon_with_gt.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/uzh_fpv) | [config](https://github.com/rpng/open_vins/blob/master/config/uzhfpv_indoor_45) |
| Indoor 45deg 14 | 211 | [rosbag](http://rpg.ifi.uzh.ch/datasets/uzh-fpv-newer-versions/v2/indoor_45_14_snapdragon_with_gt.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/uzh_fpv) | [config](https://github.com/rpng/open_vins/blob/master/config/uzhfpv_indoor_45) |
@m_enddiv
@section gs-data-kaist KAIST Urban Dataset
The [KAIST urban dataset](https://sites.google.com/view/complex-urban-dataset) @cite Jeong2019IJRR is a dataset focus on autonomous driving and localization in challenging complex urban environments.
The dataset was collected in Korea with a vehicle equipped with stereo camera pair, 2d SICK LiDARs, 3d Velodyne LiDAR, Xsens IMU, fiber optic gyro (FoG), wheel encoders, and RKT GPS.
The camera is 10 Hz, while the Xsens IMU is 100 Hz sensing rate.
A groundtruth "baseline" trajectory is also provided which is the resulting output from fusion of the FoG, RKT GPS, and wheel encoders.
@m_class{m-block m-warning}
@par Dynamic Environments
A challenging open research question is being able to handle dynamic objects seen from the cameras.
By default we rely on our tracking 8 point RANSAC to handle these dynamics objects.
In the most of the KAIST datasets the majority of the scene can be taken up by other moving vehicles, thus the performance can suffer.
Please be aware of this fact.
We recommend converting the KAIST file format into a ROS bag format.
If you are using ROS2 then you should first convert into a ROS1 then convert following the @ref dev-ros1-to-ros2 .
Follow the instructions on the [kaist2bag](https://github.com/rpng/kaist2bag) repository:
@code{.shell-session}
git clone https://github.com/irapkaist/irp_sen_msgs.git
git clone https://github.com/rpng/kaist2bag.git
@endcode
@m_class{m-block m-warning}
@par Monocular Camera
Currently there are issues with running with a monocular camera on this dataset.
This is likely due to the near-constant velocity and "smoothness" of the trajectory.
Please refer to @cite Lee2020IROS and @cite Wu2017ICRA for details.
You can also try to use the [file_player](https://github.com/irapkaist/file_player) to publish live.
It is important to *disable* the "skip stop section" to ensure that we have continuous sensor feeds.
Typically we process the datasets at 1.5x rate so we get a ~20 Hz image feed and the datasets can be processed in a more efficient manor.
@m_div{m-text-center}
| Dataset Name | Length (km) | Dataset Link | Groundtruth Traj. | Example Launch |
|-------------:|--------|--------------|------------------|------------------|
| Urban 28 | 11.47 | [download](https://sites.google.com/view/complex-urban-dataset/download-lidar-stereo?authuser=0) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/kaist) | [config](https://github.com/rpng/open_vins/blob/master/config/kaist) |
| Urban 38 | 11.42 | [download](https://sites.google.com/view/complex-urban-dataset/download-lidar-stereo?authuser=0) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/kaist) | [config](https://github.com/rpng/open_vins/blob/master/config/kaist) |
| Urban 39 | 11.06 | [download](https://sites.google.com/view/complex-urban-dataset/download-lidar-stereo?authuser=0) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/kaist) | [config](https://github.com/rpng/open_vins/blob/master/config/kaist) |
@m_enddiv
@section gs-data-kaist-vio KAIST VIO Dataset
The [KAIST VIO dataset](https://github.com/zinuok/kaistviodataset) @cite Jeon2021RAL is a dataset of a MAV in an indoor 3.15 x 3.60 x 2.50 meter environment which undergoes various trajectory motions.
The camera is intel realsense D435i 25 Hz, while the IMU is 100 Hz sensing rate from the pixelhawk 4 unit.
A groundtruth "baseline" trajectory is also provided from a OptiTrack Mocap system at 50 Hz, the bag files have the marker body frame to IMU frame already applied.
This topic has been provided in ov_data for convinces sake.
@m_div{m-text-center}
| Dataset Name | Length (km) | Dataset Link | Groundtruth Traj. | Example Launch |
|-------------:|--------|--------------|------------------|------------------|
| circle | 29.99 | [download](https://urserver.kaist.ac.kr/publicdata/KAIST_VIO_Dataset/circle/circle.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/kaist_vio) | [config](https://github.com/rpng/open_vins/blob/master/config/kaist_vio) |
| circle_fast | 64.15 | [download](https://urserver.kaist.ac.kr/publicdata/KAIST_VIO_Dataset/circle/circle_fast.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/kaist_vio) | [config](https://github.com/rpng/open_vins/blob/master/config/kaist_vio) |
| circle_head | 35.05 | [download](https://urserver.kaist.ac.kr/publicdata/KAIST_VIO_Dataset/circle/circle_head.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/kaist_vio) | [config](https://github.com/rpng/open_vins/blob/master/config/kaist_vio) |
| infinite | 29.35 | [download](https://urserver.kaist.ac.kr/publicdata/KAIST_VIO_Dataset/infinite/infinite.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/kaist_vio) | [config](https://github.com/rpng/open_vins/blob/master/config/kaist_vio) |
| infinite_fast | 54.24 | [download](https://urserver.kaist.ac.kr/publicdata/KAIST_VIO_Dataset/infinite/infinite_fast.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/kaist_vio) | [config](https://github.com/rpng/open_vins/blob/master/config/kaist_vio) |
| infinite_head | 37.45 | [download](https://urserver.kaist.ac.kr/publicdata/KAIST_VIO_Dataset/infinite/infinite_head.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/kaist_vio) | [config](https://github.com/rpng/open_vins/blob/master/config/kaist_vio) |
| rotation | 7.82 | [download](https://urserver.kaist.ac.kr/publicdata/KAIST_VIO_Dataset/rotation/rotation.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/kaist_vio) | [config](https://github.com/rpng/open_vins/blob/master/config/kaist_vio) |
| rotation_fast | 14.55 | [download](https://urserver.kaist.ac.kr/publicdata/KAIST_VIO_Dataset/rotation/rotation_fast.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/kaist_vio) | [config](https://github.com/rpng/open_vins/blob/master/config/kaist_vio) |
| square | 41.94 | [download](https://urserver.kaist.ac.kr/publicdata/KAIST_VIO_Dataset/square/square.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/kaist_vio) | [config](https://github.com/rpng/open_vins/blob/master/config/kaist_vio) |
| square_fast | 44.07 | [download](https://urserver.kaist.ac.kr/publicdata/KAIST_VIO_Dataset/square/square_fast.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/kaist_vio) | [config](https://github.com/rpng/open_vins/blob/master/config/kaist_vio) |
| square_head | 50.00 | [download](https://urserver.kaist.ac.kr/publicdata/KAIST_VIO_Dataset/square/square_head.bag) | [link](https://github.com/rpng/open_vins/tree/master/ov_data/kaist_vio) | [config](https://github.com/rpng/open_vins/blob/master/config/kaist_vio) |
@m_enddiv
*/